codefuse-ai / test-agent Goto Github PK

ImportError:
2024-04-08 09:54:28 | ERROR | stderr | CodeLlamaTokenizer requires the protobuf library but it was not found in your environment. Checkout the instructions on the
2024-04-08 09:54:28 | ERROR | stderr | installation page of its repo: https://github.com/protocolbuffers/protobuf/tree/master/python#installation and follow the ones

第三步启动前端后，访问 http://0.0.0.0:7860
显示(failed)net::ERR_EMPTY_RESPONSE

我看后端也收到请求了，但是不知道为什么访问不了

rt

环境：mac m1 pro
python version: 3.10.7

环境安装时，执行pip install -r requirements.txt，执行很久，大概6,7个小时，llama_index，langchain一直在自动试各种版本

google.protobuf.message.DecodeError: Error parsing message
请问一下我可以怎么解决呢？

也太随意了，整个环境都freeze了，里面300多个依赖包，请重新整理一份吧

需要什么硬件

部署完成，发送信息提示NETWORK ERROR DUE TO HIGH TRAFFIC. PLEASE REGENERATE OR REFRESH THIS PAGE.

请问当前的这个模型是不支持windows吗？

使用windows安装环境时报错，uvloop报错不支持windows系统

命令行依次运行指令：
python -m chat.server.controller

然后另一个命令行运行：
python -m chat.server.model_worker --model-path models/TestGPT-7B --device cpu

最后另一个命令行运行：
python -m chat.server.gradio_testgpt

无任何反应！！！
这是为什么啊，求助大神

模型是在https://modelscope.cn/models/codefuse-ai/TestGPT-7B/files clone的

执行python -m chat.server.controller，报错Error while finding module specification for 'chat.server.controller' (ModuleNotFoundError: No module named 'chat')

Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [17 lines of output]
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.3'
test.c
LINK : fatal error LNK1181: 无法打开输入文件“aio.lib”
Traceback (most recent call last):
File "", line 2, in
File "", line 34, in
File "C:\Users\33\AppData\Local\Temp\pip-install-7rd2r2v0\deepspeed_0aefcc0fcaa04450b49543c945a2152f\setup.py", line 182, in
abort(f"Unable to pre-compile {op_name}")
File "C:\Users\33\AppData\Local\Temp\pip-install-7rd2r2v0\deepspeed_0aefcc0fcaa04450b49543c945a2152f\setup.py", line 52, in abort
assert False, msg
AssertionError: Unable to pre-compile async_io
[WARNING] Torch did not find cuda available, if cross-compiling or running with cpu only you can ignore this message. Adding compute capability for Pascal, Volta, and Turing (compute capabilities 6.0, 6.1, 6.2)
DS_BUILD_OPS=1
[WARNING] async_io requires the dev libaio .so object and headers but these were not found.
[WARNING] If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
[WARNING] One can disable async_io with DS_BUILD_AIO=0
[ERROR] Unable to pre-compile async_io
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

命令：
python3 -m chat.server.model_worker --model-path ../TestGPT-7B --device cpu
报错：
/deepspeed/accelerator/real_accelerator.py", line 155, in get_accelerator
ds_accelerator = MPS_Accelerator()
TypeError: Can't instantiate abstract class MPS_Accelerator with abstract method supported_dtypes

使用命令：
python3 -m chat.server.model_worker --model-path models/testgpt --device mps

执行log记录如下：
2024-01-22 17:08:04 | INFO | model_worker | args: Namespace(host='localhost', port=21002, worker_address='http://localhost:21002', controller_address='http://localhost:21001', model_path='models/testgpt', revision='main', device='mps', gpus=None, num_gpus=1, max_gpu_memory=None, load_8bit=False, cpu_offloading=False, gptq_ckpt=None, gptq_wbits=16, gptq_groupsize=-1, gptq_act_order=False, awq_ckpt=None, awq_wbits=16, awq_groupsize=-1, model_names=None, conv_template=None, embed_in_truncate=False, limit_worker_concurrency=5, stream_interval=2, no_register=False)
2024-01-22 17:08:04 | INFO | stdout | testgpt!!!!!!
2024-01-22 17:08:04 | INFO | model_worker | Loading the model ['testgpt'] on worker c61383a5 ...
2024-01-22 17:08:04 | ERROR | stderr | Traceback (most recent call last):
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 286, in hf_raise_for_status
2024-01-22 17:08:04 | ERROR | stderr | response.raise_for_status()
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/requests/models.py", line 1021, in raise_for_status
2024-01-22 17:08:04 | ERROR | stderr | raise HTTPError(http_error_msg, response=self)
2024-01-22 17:08:04 | ERROR | stderr | requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/models/testgpt/resolve/main/tokenizer_config.json
2024-01-22 17:08:04 | ERROR | stderr |
2024-01-22 17:08:04 | ERROR | stderr | The above exception was the direct cause of the following exception:
2024-01-22 17:08:04 | ERROR | stderr |
2024-01-22 17:08:04 | ERROR | stderr | Traceback (most recent call last):
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/transformers/utils/hub.py", line 429, in cached_file
2024-01-22 17:08:04 | ERROR | stderr | resolved_file = hf_hub_download(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
2024-01-22 17:08:04 | ERROR | stderr | return fn(*args, **kwargs)
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1368, in hf_hub_download
2024-01-22 17:08:04 | ERROR | stderr | raise head_call_error
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1238, in hf_hub_download
2024-01-22 17:08:04 | ERROR | stderr | metadata = get_hf_file_metadata(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
2024-01-22 17:08:04 | ERROR | stderr | return fn(*args, **kwargs)
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 1631, in get_hf_file_metadata
2024-01-22 17:08:04 | ERROR | stderr | r = _request_wrapper(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 385, in _request_wrapper
2024-01-22 17:08:04 | ERROR | stderr | response = _request_wrapper(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/file_download.py", line 409, in _request_wrapper
2024-01-22 17:08:04 | ERROR | stderr | hf_raise_for_status(response)
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 323, in hf_raise_for_status
2024-01-22 17:08:04 | ERROR | stderr | raise RepositoryNotFoundError(message, response) from e
2024-01-22 17:08:04 | ERROR | stderr | huggingface_hub.utils._errors.RepositoryNotFoundError: 401 Client Error. (Request ID: Root=1-65ae3074-2287e248178f4d250c755ad1;7b85dc4b-9482-4cb3-95c0-2ce23b61028f)
2024-01-22 17:08:04 | ERROR | stderr |
2024-01-22 17:08:04 | ERROR | stderr | Repository Not Found for url: https://huggingface.co/models/testgpt/resolve/main/tokenizer_config.json.
2024-01-22 17:08:04 | ERROR | stderr | Please make sure you specified the correct repo_id and repo_type.
2024-01-22 17:08:04 | ERROR | stderr | If you are trying to access a private or gated repo, make sure you are authenticated.
2024-01-22 17:08:04 | ERROR | stderr | Invalid username or password.
2024-01-22 17:08:04 | ERROR | stderr |
2024-01-22 17:08:04 | ERROR | stderr | The above exception was the direct cause of the following exception:
2024-01-22 17:08:04 | ERROR | stderr |
2024-01-22 17:08:04 | ERROR | stderr | Traceback (most recent call last):
2024-01-22 17:08:04 | ERROR | stderr | File "", line 198, in _run_module_as_main
2024-01-22 17:08:04 | ERROR | stderr | File "", line 88, in _run_code
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/server/model_worker.py", line 521, in
2024-01-22 17:08:04 | ERROR | stderr | args, worker = create_model_worker()
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/server/model_worker.py", line 498, in create_model_worker
2024-01-22 17:08:04 | ERROR | stderr | worker = ModelWorker(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/server/model_worker.py", line 213, in init
2024-01-22 17:08:04 | ERROR | stderr | self.model, self.tokenizer = load_model(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/model/model_adapter.py", line 278, in load_model
2024-01-22 17:08:04 | ERROR | stderr | model, tokenizer = adapter.load_model(model_path, kwargs)
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/model/model_adapter.py", line 1589, in load_model
2024-01-22 17:08:04 | ERROR | stderr | model, tokenizer = super().load_model(model_path, from_pretrained_kwargs)
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/Users/fanjunyang/Documents/Tools/Test-Agent/chat/model/model_adapter.py", line 62, in load_model
2024-01-22 17:08:04 | ERROR | stderr | tokenizer = AutoTokenizer.from_pretrained(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 686, in from_pretrained
2024-01-22 17:08:04 | ERROR | stderr | tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/transformers/models/auto/tokenization_auto.py", line 519, in get_tokenizer_config
2024-01-22 17:08:04 | ERROR | stderr | resolved_config_file = cached_file(
2024-01-22 17:08:04 | ERROR | stderr | ^^^^^^^^^^^^
2024-01-22 17:08:04 | ERROR | stderr | File "/opt/homebrew/lib/python3.11/site-packages/transformers/utils/hub.py", line 450, in cached_file
2024-01-22 17:08:04 | ERROR | stderr | raise EnvironmentError(
2024-01-22 17:08:04 | ERROR | stderr | OSError: models/testgpt is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
2024-01-22 17:08:04 | ERROR | stderr | If this is a private repository, make sure to pass a token having permission to this repo either by logging in with huggingface-cli login or by passing token=<your_token>

可以配置什么参数之类的，可以降低性能要求？

命令：python -m chat.server.model_worker --model-path ../TestGPT-7B --device cpu --num-gpus 2